Inferring Local Structure from Pairwise Correlations
To construct models of large, multivariate complex systems, such as those in biology, one needs to constrain which variables are allowed to interact. This can be viewed as detecting "local" structures among the variables. In the context of a simple toy model of 2D natural and synthetic images, we show that pairwise correlations between the variables -- even when severely undersampled -- provide enough information to recover local relations, including the dimensionality of the data, and to reconstruct arrangement of pixels in fully scrambled images. This proves to be successful even though higher order interaction structures are present in our data. We build intuition behind the success, which we hope might contribute to modeling complex, multivariate systems and to explaining the success of modern attention-based machine learning approaches.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Zero-Shot Out-of-Distribution Detection with Feature Correlations
When presented with Out-of-Distribution (OOD) examples, deep neural networks yield confident, incorrect predictions. Detecting OOD examples is challenging, and the potential risks are high. In this paper, we propose to d…
Feature CorrelationOut-of-Distribution DetectionOut of Distribution (OOD) DetectionCausal and Local Correlations Based Network for Multivariate Time Series Classification
Recently, time series classification has attracted the attention of a large number of researchers, and hundreds of methods have been proposed. However, these methods often ignore the spatial correlations among dimensions…
Graph Neural NetworkTime SeriesTime Series ClassificationBoltzmann machine learning and regularization methods for inferring evolutionary fields and couplings from a multiple sequence alignment
The inverse Potts problem to infer a Boltzmann distribution for homologous protein sequences from their single-site and pairwise amino acid frequencies recently attracts a great deal of attention in the studies of protei…
BIG-bench Machine LearningMultiple Sequence AlignmentDependence structure of market states
We study the dependence structure of market states by estimating empirical pairwise copulas of daily stock returns. We consider both original returns, which exhibit time-varying trends and volatilities, as well as locall…
Inferring Multilateral Relations from Dynamic Pairwise Interactions
Correlations between anomalous activity patterns can yield pertinent information about complex social processes: a significant deviation from normal behavior, exhibited simultaneously by multiple pairs of actors, provide…